{"id":"W1514535095","doi":"10.48550/arxiv.1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7525,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Visualization; Gaze; Object (grammar); Backpropagation; Salient; Sequence (biology); Object detection; Machine translation; Image (mathematics); Artificial neural network; Machine learning; Computer vision; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null}